Accurate prediction of three-dimensional humanoid avatars for anthropometric modeling
Authors' conclusion
3D avatars predicted from demographic, physical, and other accessible characteristics can produce body representations with accurate anthropometric dimensions without a 3D scanner. Combining manifold regression algorithms into established body composition methods such as DXA, BIA, and other accessible methods provides new research and clinical opportunities.
Study context
- Population
- Adults; prediction equations developed in 570 adults with 3D optical scans, DXA and bioimpedance analysis (BIA); new prospective sample of 84 adultsprospective sample
- Participants
- 84 adults
- Comparison
- Manifold-regression predicted 3D avatars vs ground-truth 3D optical scanner
- Outcome
- Accuracy of avatar anthropometric dimensions (6 circumferences, 7 volumes, 7 surface areas) vs ground-truth measurements
Methodological detailsprospective
- Prospective
Performance
As reported in the abstract
Agreement of predicted vs ground-truth anthropometric estimates
Correlations between predicted and ground-truth estimates (R2s), all p < 0.001
0.75-0.99
Concordance correlation coefficients
0.80-0.99
Small but significant Bland-Altman bias (p < 0.05-0.01), measurements
13 of 20
Further findings
Mean waist to hip circumference ratio
- Predicted ratio non-significantly different from ground-truth scanner
Original publication
Accurate prediction of three-dimensional humanoid avatars for anthropometric modeling. Int J Obes (Lond). Published 24 August 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →